tulu-2-7b-hh-dpo
This model is a fine-tuned version of allenai/tulu-2-7b on the HuggingFaceH4/hh-rlhf-h4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6470
- Rewards/chosen: -0.3648
- Rewards/rejected: -0.4826
- Rewards/accuracies: 0.6129
- Rewards/margins: 0.1178
- Logps/rejected: -246.3995
- Logps/chosen: -228.8311
- Logits/rejected: -1.4327
- Logits/chosen: -1.4212
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
Framework versions
- Transformers 4.44.1
- Pytorch 2.1.2+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.